© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56617
    Prev
    Next
    INDEX
    Explanations

    cause and effect

    np_max-act · gemini-2.0-flash

    The neuron fires on causal or result-indicating verbs (e.g. “led,” “prompted,” “resulted,” “affirm,” etc.) that signal consequence or outcome.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fades
    -0.08
    amed
    -0.06
    vanced
    -0.06
     prone
    -0.06
    cheiden
    -0.06
     bru
    -0.06
     bad
    -0.06
     multiprocessing
    -0.06
     passes
    -0.06
    Decrypt
    -0.06
    POSITIVE LOGITS
    틱
    0.07
    .intent
    0.07
    計劃
    0.06
    テレビ
    0.06
     امیر
    0.06
     температу
    0.06
    σταση
    0.06
     اصفه
    0.06
    tabla
    0.06
     характериз
    0.06
    Activations Density 0.033%

    No Known Activations